INDEX

Explanations

instances where something "turns out" to be a certain way after speculation or discovery

oai_token-act-pair · gpt-3.5-turbo

the phrase "it turns out."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

shaw

-0.81

raltar

-0.75

notations

-0.73

berus

-0.73

resents

-0.70

inion

-0.70

oided

-0.69

cious

-0.69

aded

-0.68

awn

-0.67

POSITIVE LOGITS

âĶĢ

0.79

 differently

0.72

ymes

0.70

 quite

0.66

Ñĭ

0.66

Ð¼

0.65

wards

0.63

 Technician

0.61

orial

0.60

 there

0.59

Activations Density 0.030%

instances where something "turns out" to be a certain way after speculation or discovery

the phrase "it turns out."

No Comments

No Known Activations